Timbral Embeddings extractor This model produces embeddings that globally represent the timbral traits of a speaker's voice. These embeddings can be used the same way as for a classical speaker verification (ASV): in order to compare two voice signals, an embeddings vector must be computed for each of them. Then the cosine similarity between the two embeddings can be used for comparison. The main difference with classical ASV embeddings is that, here, only the timbral traits are compared. The model has been derived from the self supervised pretrained model WavLM large. The next section explains how to compute these timbral embeddings. Usage The following code snippet uses the file spk embeddings.py to build the architecture of the model. Its weights are then downloaded from this repository. The model produces normalized vectors as embeddings. The python file also contains the function to compute the timbral embeddings of an audio file. In this tutorial version, the audio file is expected to be sampled at 16kHz. Depending on the available memory (cpu or gpu), you may change the value of the max size parameter, which is used to truncate the long audio signals. finally, we can compute…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy